Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MHz
    -0.08
    orent
    -0.07
     Chat
    -0.07
    Detection
    -0.07
     Radius
    -0.07
    二是
    -0.07
    굳
    -0.07
    Help
    -0.07
    哪怕
    -0.07
     v
    -0.07
    POSITIVE LOGITS
    ἐ
    0.07
    .valor
    0.07
     Restrictions
    0.07
    ⋎
    0.07
    blocking
    0.07
    owych
    0.07
    풍
    0.07
    -feira
    0.06
    指引
    0.06
    recognized
    0.06
    Act Density 0.000%

    No Known Activations